© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 9746
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and operational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -and
    -0.16
    μη
    -0.14
    ·
    -0.13
    (!
    -0.13
    ">-->↵
    -0.13
    /*.
    -0.13
    -plus
    -0.13
    ï¼ļ↵↵
    -0.13
    ิà¸ĩ
    -0.12
    ãĥĬãĥ«
    -0.12
    POSITIVE LOGITS
     –
    0.55
     â
    0.52
     -
    0.47
     Â
    0.45
     —
    0.43
     �
    0.41
     âĪĴ
    0.40
     âĶĢ
    0.40
     ï¼į
    0.39
     --
    0.38
    Activations Density 0.126%

    No Known Activations